Skip to content

Improve GEMM performance of shape 4096x8x128x16384 #2646

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 11, 2024
Merged

Improve GEMM performance of shape 4096x8x128x16384 #2646

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9bdca90
improve
yudongsi Nov 7, 2024
674bd20
Merge branch 'main' into yudong/tune-in-ci
yudongsi Nov 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions benchmarks/triton_kernels_benchmark/gemm_benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,8 +129,8 @@ def matmul_kernel_with_block_pointers_batched(
stride_cz: tl.constexpr, stride_cm: tl.constexpr, stride_cn: tl.constexpr,
# Meta-parameters
BLOCK_SIZE_M: tl.constexpr, BLOCK_SIZE_N: tl.constexpr, BLOCK_SIZE_K: tl.constexpr, GROUP_SIZE_M: tl.constexpr):
bid = tl.program_id(axis=0)
pid = tl.program_id(axis=1)
bid = tl.program_id(axis=1)
pid = tl.program_id(axis=0)
num_pid_m = tl.cdiv(M, BLOCK_SIZE_M)
num_pid_n = tl.cdiv(N, BLOCK_SIZE_N)
num_pid_in_group = GROUP_SIZE_M * num_pid_n
Expand Down Expand Up @@ -186,8 +186,8 @@ def matmul(a, b, c, transpose_a=False, transpose_b=False):
B = a.shape[0]
# 1D launch kernel where each block gets its own program.
grid = lambda META: (
B,
triton.cdiv(M, META['BLOCK_SIZE_M']) * triton.cdiv(N, META['BLOCK_SIZE_N']),
B,
)
matmul_kernel_with_block_pointers_batched[grid](
a, b, c, #
Expand Down